web-csv-toolbox 0.1.0 → 0.3.0

package/lib/index.js

@@ -1,33 +1,11 @@
-/**
- * FiledDelimiter is a symbol for field delimiter of CSV.
- */
 const FieldDelimiter = Symbol.for("web-streams-csv.FieldDelimiter");
-/**
- * RecordDelimiter is a symbol for record delimiter of CSV.
- */
 const RecordDelimiter = Symbol.for("web-streams-csv.RecordDelimiter");
-/**
- * Field is a symbol for field of CSV.
- */
 const Field = Symbol.for("web-streams-csv.Field");
-
 const CR = "\r";
 const CRLF = "\r\n";
 const LF = "\n";
-/**
- * COMMA is a symbol for comma(,).
- */
 const COMMA = ",";
-/**
- * DOUBLE_QUATE is a symbol for double quate(").
- */
 const DOUBLE_QUATE = '"';
-
-/**
- * Assert that the options are valid.
- *
- * @param options The options to assert.
- */
 function assertCommonOptions(options) {
   if (typeof options.quotation === "string" && options.quotation.length === 0) {
     throw new Error("quotation must not be empty");
@@ -50,42 +28,9 @@ function assertCommonOptions(options) {
     );
   }
 }
-
-/**
- * Escape a string for use in a regular expression.
- *
- * @see {@link https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_expressions#escaping Regular expressions#Escaping | MDN}
- * @param v string to escape
- * @returns escaped string
- */
 function escapeRegExp(v) {
   return v.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
 }
-
-/**
- * A transform stream that converts a stream of tokens into a stream of rows.
- *
- * @example Parse a CSV with headers by data
- * ```ts
- * new ReadableStream({
- *  start(controller) {
- *   controller.enqueue("name,age\r\n");
- *  controller.enqueue("Alice,20\r\n");
- * controller.close();
- * }
- * })
- * .pipeThrough(new LexerTransformer())
- * .pipeTo(new WritableStream({ write(token) { console.log(token); }}));
- * // { type: Field, value: "name" }
- * // { type: FieldDelimiter, value: "," }
- * // { type: Field, value: "age" }
- * // { type: RecordDelimiter, value: "\r\n" }
- * // { type: Field, value: "Alice" }
- * // { type: FieldDelimiter, value: "," }
- * // { type: Field, value: "20" }
- * // { type: RecordDelimiter, value: "\r\n" }
- * ```
- */
 class LexerTransformer extends TransformStream {
   #demiliter;
   #demiliterLength;
@@ -161,49 +106,38 @@ class LexerTransformer extends TransformStream {
     if (this.#buffer.length === 0) {
       return null;
     }
-    // Check for CRLF
     if (this.#buffer.startsWith(CRLF)) {
       this.#buffer = this.#buffer.slice(2);
       return { type: RecordDelimiter, value: CRLF };
     }
-    // Check for LF
     if (this.#buffer.startsWith(LF)) {
       this.#buffer = this.#buffer.slice(1);
       return { type: RecordDelimiter, value: LF };
     }
-    // Check for Delimiter
     if (this.#buffer.startsWith(this.#demiliter)) {
       this.#buffer = this.#buffer.slice(this.#demiliterLength);
       return { type: FieldDelimiter, value: this.#demiliter };
     }
-    // Check for Quoted String
     if (this.#buffer.startsWith(this.#quotation)) {
-      // If we're flushing and the buffer doesn't end with a quote, then return null
-      // because we're not done with the quoted string
       if (flush === false && this.#buffer.endsWith(this.#quotation)) {
         return null;
       }
       return this.extractQuotedString();
     }
-    // Check for Unquoted String
     const match = this.#matcher.exec(this.#buffer);
     if (match) {
-      // If we're flushing and the match doesn't consume the entire buffer,
-      // then return null
       if (flush === false && match[0].length === this.#buffer.length) {
         return null;
       }
       this.#buffer = this.#buffer.slice(match[0].length);
       return { type: Field, value: match[0] };
     }
-    // Otherwise, return null
     return null;
   }
   extractQuotedString() {
-    let end = this.#quotationLength; // Skip the opening quote
+    let end = this.#quotationLength;
     let value = "";
     while (end < this.#buffer.length) {
-      // Escaped quote
       if (
         this.#buffer.slice(end, end + this.#quotationLength) ===
           this.quotation &&
@@ -216,7 +150,6 @@ class LexerTransformer extends TransformStream {
         end += this.#quotationLength * 2;
         continue;
       }
-      // Closing quote
       if (
         this.#buffer.slice(end, end + this.#quotationLength) === this.quotation
       ) {
@@ -226,52 +159,9 @@ class LexerTransformer extends TransformStream {
       value += this.#buffer[end];
       end++;
     }
-    // If we get here, we've reached the end of the buffer
     return null;
   }
 }
-
-/**
- * A transform stream that converts a stream of tokens into a stream of rows.
- * @template Header The type of the header row.
- * @param options The options for the parser.
- *
- * @example Parse a CSV with headers by data
- *  ```ts
- * new ReadableStream({
- *   start(controller) {
- *     controller.enqueue("name,age\r\n");
- *     controller.enqueue("Alice,20\r\n");
- *     controller.enqueue("Bob,25\r\n");
- *     controller.enqueue("Charlie,30\r\n");
- *     controller.close();
- *   })
- *   .pipeThrough(new LexerTransformer())
- *   .pipeThrough(new RecordAssemblerTransformar())
- *   .pipeTo(new WritableStream({ write(row) { console.log(row); }}));
- * // { name: "Alice", age: "20" }
- * // { name: "Bob", age: "25" }
- * // { name: "Charlie", age: "30" }
- * ```
- *
- * @example Parse a CSV with headers by options
- * ```ts
- * new ReadableStream({
- *   start(controller) {
- *     controller.enqueue("Alice,20\r\n");
- *     controller.enqueue("Bob,25\r\n");
- *     controller.enqueue("Charlie,30\r\n");
- *     controller.close();
- *   }
- * })
- * .pipeThrough(new LexerTransformer())
- * .pipeThrough(new RecordAssemblerTransformar({ header: ["name", "age"] }))
- * .pipeTo(new WritableStream({ write(row) { console.log(row); }}));
- * // { name: "Alice", age: "20" }
- * // { name: "Bob", age: "25" }
- * // { name: "Charlie", age: "30" }
- * ```
- */
 class RecordAssemblerTransformar extends TransformStream {
   #fieldIndex = 0;
   #row = [];
@@ -301,7 +191,6 @@ class RecordAssemblerTransformar extends TransformStream {
                 controller.enqueue(record);
               }
             }
-            // Reset the row fields buffer.
             this.#fieldIndex = 0;
             this.#row = new Array(this.#header?.length);
             this.#darty = false;
@@ -310,7 +199,6 @@ class RecordAssemblerTransformar extends TransformStream {
       },
       flush: (controller) => {
         if (this.#fieldIndex !== 0 && this.#header !== undefined) {
-          // console.log('B', this.#row)
           if (this.#darty) {
             const record = Object.fromEntries(
               this.#header
@@ -336,7 +224,6 @@ class RecordAssemblerTransformar extends TransformStream {
     }
   }
 }
-
 class SingleValueReadableStream extends ReadableStream {
   constructor(value) {
     super({
@@ -347,7 +234,6 @@ class SingleValueReadableStream extends ReadableStream {
     });
   }
 }
-
 async function toArray(...args) {
   const rows = [];
   for await (const row of this(...args)) {
@@ -355,13 +241,6 @@ async function toArray(...args) {
   }
   return rows;
 }
-
-/**
- * Parse CSV string to records.
- *
- * @param stream CSV string stream to parse
- * @param options Parsing options. See {@link ParseOptions}.
- */
 async function* parseStringStream(stream, options) {
   let controller;
   const readable = new ReadableStream({
@@ -387,49 +266,28 @@ async function* parseStringStream(stream, options) {
     reader.releaseLock();
   }
 }
-(function (parseStringStream) {})(
-  parseStringStream || (parseStringStream = {}),
-);
-parseStringStream.toArray = toArray;
-
-/**
- * Parse CSV string to records.
- *
- * @param csv CSV string to parse
- * @param options Parsing options. See {@link ParseOptions}.
- */
-async function* streamingParse(csv, options) {
+((parseStringStream) => {
+  parseStringStream.toArray = toArray;
+})(parseStringStream || (parseStringStream = {}));
+async function* parseString(csv, options) {
   yield* parseStringStream(new SingleValueReadableStream(csv), options);
 }
-(function (streamingParse) {})(streamingParse || (streamingParse = {}));
-streamingParse.toArray = toArray;
-
-/**
- * Parse CSV to records.
- * This function is for parsing a binary stream.
- *
- * @remarks
- * If you want to parse a string, use {@link streamingParse}.
- * @param stream CSV string to parse
- * @param options Parsing options. See {@link ParseBinaryOptions}.
- */
+((parseString) => {
+  parseString.toArray = toArray;
+})(parseString || (parseString = {}));
 async function* parseBinaryStream(stream, options) {
   const { charset, fatal, ignoreBOM, decomposition } = options ?? {};
   yield* parseStringStream(
     [
-      // NOTE: if decompression is undefined, it will be ignored.
       ...(decomposition ? [new DecompressionStream(decomposition)] : []),
-      // NOTE: if charset is undefined, it will be decoded as utf-8.
       new TextDecoderStream(charset, { fatal, ignoreBOM }),
     ].reduce((stream, transformer) => stream.pipeThrough(transformer), stream),
     options,
   );
 }
-(function (parseBinaryStream) {})(
-  parseBinaryStream || (parseBinaryStream = {}),
-);
-parseBinaryStream.toArray = toArray;
-
+((parseBinaryStream) => {
+  parseBinaryStream.toArray = toArray;
+})(parseBinaryStream || (parseBinaryStream = {}));
 function parseMime(contentType) {
   const [type, ...parameters] = contentType.split(";");
   const result = {
@@ -442,7 +300,6 @@ function parseMime(contentType) {
   }
   return result;
 }
-
 function parseResponse(response, options) {
   const { headers } = response;
   const contentType = headers.get("content-type") ?? "text/csv";
@@ -452,8 +309,6 @@ function parseResponse(response, options) {
   }
   const decomposition = headers.get("content-encoding") ?? undefined;
   const charset = mime.parameters.charset ?? "utf-8";
-  // TODO: Support header=present and header=absent
-  // const header = mime.parameters.header ?? "present";
   if (response.body === null) {
     throw new Error("Response body is null");
   }
@@ -463,75 +318,35 @@ function parseResponse(response, options) {
     ...options,
   });
 }
-(function (parseResponse) {})(parseResponse || (parseResponse = {}));
-parseResponse.toArray = toArray;
-
-/**
- * Parse CSV Stream to records.
- * string and Uint8Array are supported.
- *
- * @remarks
- * {@link parseStringStream} and {@link parseBinaryStream} are used internally.
- * If you known the type of the stream, it performs better to use them directly.
- *
- * If you want to parse a string, use {@link parseStringStream}.
- * If you want to parse a Uint8Array, use {@link parseBinaryStream}.
- *
- * @param csv CSV string to parse
- * @param options Parsing options. See {@link ParserOptions}.
- */
+((parseResponse) => {
+  parseResponse.toArray = toArray;
+})(parseResponse || (parseResponse = {}));
 async function* parseStream(stream, options) {
   const [branch1, branch2] = stream.tee();
   const reader1 = branch1.getReader();
   const { value: firstChunk } = await reader1.read();
   reader1.releaseLock();
-  switch (true) {
-    case typeof firstChunk === "string":
-      yield* parseStringStream(branch2, options);
-      break;
-    case firstChunk instanceof Uint8Array:
-      yield* parseBinaryStream(branch2, options);
-      break;
+  if (typeof firstChunk === "string") {
+    yield* parseStringStream(branch2, options);
+  } else if (firstChunk instanceof Uint8Array) {
+    yield* parseBinaryStream(branch2, options);
   }
 }
-(function (parseStream) {})(parseStream || (parseStream = {}));
-parseStream.toArray = toArray;
-
-/**
- * Parse CSV to records.
- *
- * {@link String}, {@link Uint8Array}, ReadableStream<string | Uint8Array> and Response are supported.
- *
- * @remarks
- * {@link streamingParse}, {@link parseBinaryStream},
- * {@link parseStringStream} and {@link parseResponse} are used internally.
- * If you known the type of the stream, it performs better to use them directly.
- *
- * If you want to parse a string, use {@link streamingParse}.
- * If you want to parse a Uint8Array, use {@link parseStream}.
- * If you want to parse a ReadableStream<string>, use {@link parseStringStream}.
- * If you want to parse a ReadableStream<Uint8Array>, use {@link parseBinaryStream}.
- * If you want to parse a Response, use {@link parseResponse}.
- *
- * @param csv CSV string to parse
- * @param options Parsing options. See {@link ParseOptions}.
- */
+((parseStream) => {
+  parseStream.toArray = toArray;
+})(parseStream || (parseStream = {}));
 async function* parse(csv, options) {
-  switch (true) {
-    case typeof csv === "string":
-      yield* streamingParse(csv, options);
-      break;
-    case csv instanceof ReadableStream:
-      yield* parseStream(csv, options);
-      break;
-    case csv instanceof Response:
-      yield* parseResponse(csv, options);
-      break;
+  if (typeof csv === "string") {
+    yield* parseString(csv, options);
+  } else if (csv instanceof ReadableStream) {
+    yield* parseStream(csv, options);
+  } else if (csv instanceof Response) {
+    yield* parseResponse(csv, options);
   }
 }
-(function (parse) {})(parse || (parse = {}));
-parse.toArray = toArray;
-
+((parse) => {
+  parse.toArray = toArray;
+})(parse || (parse = {}));
 export {
   Field,
   FieldDelimiter,
@@ -540,6 +355,8 @@ export {
   RecordDelimiter,
   parse,
   parseBinaryStream,
+  parseResponse,
+  parseStream,
+  parseString,
   parseStringStream,
-  streamingParse,
 };

package/lib/index.umd.js

@@ -0,0 +1 @@
+!function(e,t){"object"==typeof exports&&"undefined"!=typeof module?t(exports):"function"==typeof define&&define.amd?define(["exports"],t):t((e="undefined"!=typeof globalThis?globalThis:e||self).CSV={})}(this,(function(e){"use strict";const t=Symbol.for("web-streams-csv.FieldDelimiter"),i=Symbol.for("web-streams-csv.RecordDelimiter"),r=Symbol.for("web-streams-csv.Field"),n="\n";function s(e){return e.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")}class o extends TransformStream{#e;#t;#i;#r;#n;#s="";get demiliter(){return this.#e}get quotation(){return this.#i}constructor({demiliter:e=",",quotation:t='"'}={}){!function(e){if("string"==typeof e.quotation&&0===e.quotation.length)throw new Error("quotation must not be empty");if("string"==typeof e.demiliter&&0===e.demiliter.length)throw new Error("demiliter must not be empty");if(e.quotation.includes(n)||e.quotation.includes("\r"))throw new Error("quotation must not include CR or LF");if(e.demiliter.includes(n)||e.demiliter.includes("\r"))throw new Error("demiliter must not include CR or LF");if(e.demiliter.includes(e.quotation)||e.quotation.includes(e.demiliter))throw new Error("demiliter and quotation must not include each other as a substring")}({demiliter:e,quotation:t}),super({transform:(e,t)=>{if(0!==e.length){this.#s+=e;for(const e of this.#o({flush:!1}))t.enqueue(e)}},flush:e=>{for(const t of this.#o({flush:!0}))e.enqueue(t)}}),this.#e=e,this.#t=e.length,this.#i=t,this.#r=t.length;const i=s(e),r=s(t);this.#n=new RegExp(`^(?:(?!${r})(?!${i})(?![\\r\\n]))([\\S\\s\\uFEFF\\xA0]+?)(?=${r}|${i}|\\r|\\n|$)`)}*#o({flush:e}){let n=null;for(let s;s=this.#a({flush:e});)switch(s.type){case r:n?n.value+=s.value:n=s;break;case t:case i:n&&(yield n,n=null),yield s}n&&(yield n)}#a({flush:e=!1}={}){if(0===this.#s.length)return null;if(this.#s.startsWith("\r\n"))return this.#s=this.#s.slice(2),{type:i,value:"\r\n"};if(this.#s.startsWith(n))return this.#s=this.#s.slice(1),{type:i,value:n};if(this.#s.startsWith(this.#e))return this.#s=this.#s.slice(this.#t),{type:t,value:this.#e};if(this.#s.startsWith(this.#i))return!1===e&&this.#s.endsWith(this.#i)?null:this.extractQuotedString();const s=this.#n.exec(this.#s);return s?!1===e&&s[0].length===this.#s.length?null:(this.#s=this.#s.slice(s[0].length),{type:r,value:s[0]}):null}extractQuotedString(){let e=this.#r,t="";for(;e<this.#s.length;)if(this.#s.slice(e,e+this.#r)!==this.quotation||this.#s.slice(e+this.#r,e+2*this.#r)!==this.quotation){if(this.#s.slice(e,e+this.#r)===this.quotation)return this.#s=this.#s.slice(e+this.#r),{type:r,value:t};t+=this.#s[e],e++}else t+=this.quotation,e+=2*this.#r;return null}}class a extends TransformStream{#u=0;#h=[];#l;#f=!1;constructor(e={}){super({transform:(e,n)=>{switch(e.type){case r:this.#f=!0,this.#h[this.#u]=e.value;break;case t:this.#u++;break;case i:if(void 0===this.#l)this.#d(this.#h);else if(this.#f){const e=Object.fromEntries(this.#l.filter((e=>e)).map(((e,t)=>[e,this.#h.at(t)])));n.enqueue(e)}this.#u=0,this.#h=new Array(this.#l?.length),this.#f=!1}},flush:e=>{if(0!==this.#u&&void 0!==this.#l&&this.#f){const t=Object.fromEntries(this.#l.filter((e=>e)).map(((e,t)=>[e,this.#h.at(t)])));e.enqueue(t)}}}),void 0!==e.header&&Array.isArray(e.header)&&this.#d(e.header)}#d(e){if(this.#l=e,0===this.#l.length)throw new Error("The header must not be empty.");if(new Set(this.#l).size!==this.#l.length)throw new Error("The header must not contain duplicate fields.")}}class u extends ReadableStream{constructor(e){super({start(t){t.enqueue(e),t.close()}})}}async function h(...e){const t=[];for await(const i of this(...e))t.push(i);return t}async function*l(e,t){let i;const r=new ReadableStream({start:e=>i=e});await e.pipeThrough(new o(t)).pipeThrough(new a(t)).pipeTo(new WritableStream({write:e=>i.enqueue(e),close:()=>i.close()}));const n=r.getReader();try{for(;;){const{value:e,done:t}=await n.read();if(t)break;yield e}}finally{n.releaseLock()}}async function*f(e,t){yield*l(new u(e),t)}async function*d(e,t){const{charset:i,fatal:r,ignoreBOM:n,decomposition:s}=t??{};yield*l([...s?[new DecompressionStream(s)]:[],new TextDecoderStream(i,{fatal:r,ignoreBOM:n})].reduce(((e,t)=>e.pipeThrough(t)),e),t)}function c(e,t){const{headers:i}=e,r=i.get("content-type")??"text/csv",n=function(e){const[t,...i]=e.split(";"),r={type:t.trim(),parameters:{}};for(const e of i){const[t,i]=e.split("=");r.parameters[t.trim()]=i.trim()}return r}(r);if("text/csv"!==n.type)throw new Error(`Invalid mime type: ${r}`);const s=i.get("content-encoding")??void 0,o=n.parameters.charset??"utf-8";if(null===e.body)throw new Error("Response body is null");return d(e.body,{decomposition:s,charset:o,...t})}async function*m(e,t){const[i,r]=e.tee(),n=i.getReader(),{value:s}=await n.read();n.releaseLock(),"string"==typeof s?yield*l(r,t):s instanceof Uint8Array&&(yield*d(r,t))}async function*y(e,t){"string"==typeof e?yield*f(e,t):e instanceof ReadableStream?yield*m(e,t):e instanceof Response&&(yield*c(e,t))}!function(e){e.toArray=h}(l||(l={})),function(e){e.toArray=h}(f||(f={})),function(e){e.toArray=h}(d||(d={})),function(e){e.toArray=h}(c||(c={})),function(e){e.toArray=h}(m||(m={})),function(e){e.toArray=h}(y||(y={})),e.Field=r,e.FieldDelimiter=t,e.LexerTransformer=o,e.RecordAssemblerTransformar=a,e.RecordDelimiter=i,e.parse=y,e.parseBinaryStream=d,e.parseResponse=c,e.parseStream=m,e.parseString=f,e.parseStringStream=l}));

package/package.json

@@ -1,11 +1,12 @@
 {
   "name": "web-csv-toolbox",
-  "version": "0.1.0",
+  "version": "0.3.0",
   "description": "A CSV Toolbox utilizing Web Standard APIs.",
   "type": "module",
   "main": "lib/index.js",
   "module": "lib/index.js",
   "types": "lib/index.d.ts",
+  "unpkg": "lib/index.umd.js",
   "engines": {
     "node": ">=18.0.0"
   },
@@ -27,7 +28,7 @@
     "lint": "biome lint .",
     "check": "biome check src --apply",
     "check:no-apply": "biome check src",
-    "build": "rollup -c rollup.config.ts --configPlugin rollup-plugin-typescript2 && biome format lib --write",
+    "build": "rollup -c rollup.config.ts --configPlugin rollup-plugin-typescript2 && biome check lib --apply",
     "prepare": "husky install"
   },
   "repository": {
@@ -45,12 +46,13 @@
   "bugs": {
     "url": "https://github.com/kamiazya/web-csv-toolbox/issues"
   },
-  "homepage": "https://github.com/kamiazya/web-csv-toolbox#readme",
+  "homepage": "https://kamiazya.github.io/web-csv-toolbox/",
   "devDependencies": {
     "@biomejs/biome": "1.4.1",
     "@changesets/changelog-github": "^0.5.0",
     "@changesets/cli": "^2.27.1",
     "@fast-check/vitest": "^0.0.9",
+    "@rollup/plugin-terser": "^0.4.4",
     "changesets-github-release": "^0.1.0",
     "husky": "^8.0.0",
     "jsdom": "^23.0.1",
@@ -60,7 +62,8 @@
     "rollup-plugin-dts": "^6.1.0",
     "rollup-plugin-typescript2": "^0.36.0",
     "typedoc": "^0.25.4",
+    "typedoc-plugin-mdn-links": "^3.1.9",
     "typescript": "^5.3.2",
     "vitest": "^1.1.0"
   }
-}
+}